Alternatives and similar repositories for emergent-misalignment

Users that are interested in emergent-misalignment are comparing it to the libraries listed below

• goodfire-ai / r1-interpretability
  Open source interpretability artefacts for R1.
  ☆163Updated 7 months ago
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆214Updated last year
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆299Updated 5 months ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆129Updated 8 months ago
• UKGovernmentBEIS / inspect_evals
  Collection of evals for Inspect AI
  ☆284Updated this week
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆225Updated last week
• safety-research / persona_vectors
  Persona Vectors: Monitoring and Controlling Character Traits in Language Models
  ☆284Updated 3 months ago
• METR / task-standard
  METR Task Standard
  ☆167Updated 9 months ago
• hijohnnylin / neuronpedia
  open source interpretability platform 🧠
  ☆486Updated this week
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆227Updated 11 months ago
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆242Updated last year
• METR / public-tasks
  ☆106Updated last week
• METR / vivaria
  Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
  ☆120Updated last week
• UKGovernmentBEIS / control-arena
  ControlArena is a collection of settings, model organisms and protocols - for running control experiments.
  ☆128Updated this week
• google-deepmind / mishax
  ☆143Updated 2 months ago
• anthropics / attribution-graphs-frontend
  https://transformer-circuits.pub/2025/attribution-graphs/methods.html
  ☆90Updated 7 months ago
• EleutherAI / sparsify
  Sparsify transformers with SAEs and transcoders
  ☆654Updated last week
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆284Updated last year
• LeonGuertler / TextArena
  A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning
  ☆311Updated 3 weeks ago
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆193Updated last year
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆122Updated last year
• jacobdunefsky / transcoder_circuits
  ☆188Updated last year
• stanfordnlp / axbench
  Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
  ☆141Updated 4 months ago
• anthropic-experimental / agentic-misalignment
  ☆520Updated 5 months ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆301Updated 11 months ago
• redwoodresearch / alignment_faking_public
  ☆81Updated last month
• google-deepmind / dangerous-capability-evaluations
  ☆62Updated last month
• saprmarks / feature-circuits
  ☆194Updated last month
• princeton-pli / hal-harness
  ☆186Updated last week
• haizelabs / Awesome-LLM-Judges
  ⚖️ Awesome LLM Judges ⚖️
  ☆133Updated 6 months ago